team-refactor

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) to gather codebase context and metadata. These commands (e.g., git diff, gh pr view) are standard for developer tools and are used here to read-only the necessary context for refactoring analysis.\n- [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub, creating a surface for indirect prompt injection.\n
  • Ingestion points: Data is ingested from Pull Request bodies, diffs, and Issue comments via gh commands in SKILL.md.\n
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore' commands to isolate external content from the sub-agents' primary instructions.\n
  • Capability inventory: The skill spawns general-purpose sub-agents to analyze the data. While they have broad analytical capabilities, the skill's defined output is restricted to generating a written plan rather than performing automated file writes or deletions.\n
  • Sanitization: There is no evidence of sanitization or validation performed on the text retrieved from GitHub before it is processed by the AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:35 PM